Automated Detection of Intracranial Large Vessel Occlusions on Computed Tomography Angiography

Abstract

Background and Purpose— Endovascular thrombectomy is highly effective in acute ischemic stroke patients with an anterior circulation large vessel occlusion (LVO), decreasing morbidity and mortality. Accurate and prompt identification of LVOs is imperative because these patients have large volumes of tissue that are at risk of infarction without timely reperfusion, and the treatment window is limited to 24 hours. We assessed the accuracy and speed of a commercially available fully automated LVO-detection tool in a cohort of patients presenting to a regional hospital with suspected stroke. Methods— Consecutive patients who underwent multimodal computed tomography with thin-slice computed tomography angiography between January 1, 2017 and December 31, 2018 for suspected acute ischemic stroke within 24 hours of onset were retrospectively identified. The multimodal computed tomographies were assessed by 2 neuroradiologists in consensus for the presence of an intracranial anterior circulation LVO or M2-segment middle cerebral artery occlusion (the reference standard). The patients’ computed tomography angiographies were then processed using an automated LVO-detection algorithm (RAPID CTA). Receiver-operating characteristic analysis was used to determine sensitivity, specificity, and negative predictive value of the algorithm for detection of (1) an LVO and (2) either an LVO or M2-segment middle cerebral artery occlusion. Results— CTAs from 477 patients were analyzed (271 men and 206 women; median age, 71; IQR, 60–80). Median processing time was 158 seconds (IQR, 150–167 seconds). Seventy-eight patients had an anterior circulation LVO, and 28 had an isolated M2-segment middle cerebral artery occlusion. The sensitivity, negative predictive value, and specificity were 0.94, 0.98, and 0.76, respectively for detection of an intracranial LVO and 0.92, 0.97, and 0.81, respectively for detection of either an intracranial LVO or M2-segment middle cerebral artery occlusion. Conclusions— The fully automated algorithm had very high sensitivity and negative predictive value for LVO detection with fast processing times, suggesting that it can be used in the emergent setting as a screening tool to alert radiologists and expedite formal diagnosis.

Detecting Large Vessel Occlusion at Multiphase CT Angiography by Using a Deep Convolutional Neural Network

“…viz.ai), to our knowledge, this is the first study to use a convolutional neural network to identify LVO by using multiphase CT angiography images. Published results evaluating these commercial platforms that used single-phase CT angiography examinations demonstrated an overall AUC, sensitivity, and specificity of 0.86, 0.92, and 0.81, respectively, for the rapid CT angiography algorithm (28) and sensitivity of 0.82 and specificity of 0.94 for the Viz.ai algorithm (29). However, our study achieved an overall AUC of 0.97 without cutoffs, sensitivity of 1.00, and specificity of 0.77.…”

Middle Cerebral Artery Duplication: A Near Miss for Stroke Thrombectomy

“…To prevent this, we suggest the clinician, who has a high clinical suspicion for ELVO, as in the case described above, even if a CTA is negative, to continue with CT perfusion so as to not miss a stroke in a patient with MCA duplication or another similar anomaly. Automated applications for ELVO detection such as those provided by RAPID.AI and VIZ.AI are designed to automatically identify potential thrombectomy-eligible cases on CT or MR angiogram images [ 5 , 6 ]. While artificial intelligence-driven algorithms may improve ELVO detection, physicians managing acute stroke cases should be mindful that cases with rare anatomical variants such as the one reported here may not be included in training or validation protocols, increasing the possibility of false-negative findings [ 7 ].…”

Performance of Automated Attenuation Measurements at Identifying Large Vessel Occlusion Stroke on CT Angiography

“…Vendors include ischemaView (RAPID CTA, is-chemaView inc., Menlo Park, CA, USA), Viz.ai (Viz LVO, Viz.ai, San Francisco, CA, USA), Nico.lab (Stroke Viewer, nico-lab, Amsterdam, The Netherlands) or Brainomix (e-CTA, Brainomix, Oxford, UK). Reported sensitivities for LVO detection range between 0.81 and 0.97, although data are not complete for all vendors [16][17][18][19][20].…”